Comments (8)
The transformation we found last time that causes numerical overflow is exp()/log() for positive numbers. When we move in R towards a larger value, and call exp() to convert back to X, the numerical overflow occurs.
Do you think it is feasible we just use another transform for positive numbers? Say:
- x -> x, for x >= 1
- x -> log(x), for x < 1
This function is still continuous as both log(x) and x has the same derivative at x = 1, and will not cause numerical overflow. But I'm not sure if it will broken the leapfrog integration?
from turing.jl.
There are two variables that determines how far HMC travels in each dimension, namely the momentum
variable and n_step*ϵ
. It is probably better to first try introducing a pre-conditioning (diagonal) mass matrix and see whether it helps resolving the large step size issue.
from turing.jl.
Zoubin said it's probably better to run 10 chains of 100 samples instead of 1 chain of 1000 samples to compute the pre-conditioning matrix.
from turing.jl.
@yebai Are you working on this? If not I'd like to pick it up and work on it.
from turing.jl.
@yebai Page 47 of the CmdStan handbook refers the three mode of pre-cond in Stan as "unit", "diag" and "dense". I guess "unit" just means without pre-cond, "diag" is diagonal of the co-variance and "dense" is probably using full co-variance. Is my understanding correct?
from turing.jl.
yes, that's correct.
from turing.jl.
Let's do the dense
preconditioning matrix in the future.
from turing.jl.
Closed in favour of #279
from turing.jl.
Related Issues (20)
- Better return type for mode estimation
- Undeterministic test failure HOT 2
- Tests to check that the correct AD method is actually used
- Setup continuous benchmarking for Tuirng/DynamicPPL
- Problem with using `predict` with vector valued random variables HOT 16
- Turing guaranteed to error (when compiled with GPUCompiler) HOT 6
- Style Guide and Style Checker HOT 13
- Dependent uniform variables not working correctly HOT 2
- Add `Tapir` to Turing's AD test suite
- Implementing `adtype` for closely linked "external" samplers / adding metric warm-up HOT 2
- Constrained or partitioned inference for Turing models.
- Compat issue HOT 13
- missing keyword arguments not property processed HOT 5
- Enable Aqua.test_ambiguities
- Progress reporting in parallel sampling HOT 3
- Using @distributed to accelerate but getting wrong results
- Mode estimation's support of Pathfinder integration HOT 5
- Docs on SGHMC / SGLD? HOT 4
- Failing in precompiling dependencies HOT 2
- AbstractMCMC docs page out of date HOT 1
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from turing.jl.